Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kedah
    -0.08
     jeu
    -0.08
    ათი
    -0.07
    (exchange
    -0.07
    双方
    -0.07
    zeuge
    -0.07
     Spazier
    -0.07
    (posts
    -0.07
    spiele
    -0.07
     ಇಬ್ಬ
    -0.07
    POSITIVE LOGITS
    —all
    0.09
     ஆகிய
    0.09
     semuanya
    0.08
    。それ
    0.08
     എന്നിവ
    0.08
    ��
    0.08
     hinweg
    0.08
     Nadia
    0.08
    enco
    0.07
    fortawesome
    0.07
    Act Density 0.057%

    No Known Activations